FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation

TL;DR

FlowEO introduces a flow-matching generative framework for unsupervised domain adaptation in Earth observation, effectively handling diverse distribution shifts and improving classification and segmentation performance across multiple datasets.

Contribution

The paper presents FlowEO, a novel flow-matching based generative approach for image-space unsupervised domain adaptation in remote sensing, addressing complex distribution shifts.

Findings

FlowEO outperforms existing image translation methods in domain adaptation tasks.

Achieves comparable or superior perceptual image quality.

Effective across diverse datasets and adaptation scenarios.

Abstract

The increasing availability of Earth observation data offers unprecedented opportunities for large-scale environmental monitoring and analysis. However, these datasets are inherently heterogeneous, stemming from diverse sensors, geographical regions, acquisition times, and atmospheric conditions. Distribution shifts between training and deployment domains severely limit the generalization of pretrained remote sensing models, making unsupervised domain adaptation (UDA) crucial for real-world applications. We introduce FlowEO, a novel framework that leverages generative models for image-space UDA in Earth observation. We leverage flow matching to learn a semantically preserving mapping that transports from the source to the target image distribution. This allows us to tackle challenging domain adaptation configurations for classification and semantic segmentation of Earth observation images. We conduct extensive experiments across four datasets covering adaptation scenarios such as SAR to optical translation and temporal and semantic shifts caused by natural disasters. Experimental results demonstrate that FlowEO outperforms existing image translation approaches for domain adaptation while achieving on-par or better perceptual image quality, highlighting the potential of flow-matching-based UDA for remote sensing.